© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2768
    Prev
    Next
    INDEX
    Explanations

    German language text that contains specific grammatical structures related to verbs

    oai_token-act-pair · gemini-2.0-flash

    suffixes or endings in names or terms

    np_token-act-pair-logits · gpt-4o-mini

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.65
    hoeddwyd
    -0.58
     springfox
    -0.56
    TagMode
    -0.55
     Ananda
    -0.52
    JspWriter
    -0.50
    basicConfig
    -0.50
    PullParser
    -0.50
    झे
    -0.48
    ParallelGroup
    -0.48
    POSITIVE LOGITS
    selen
    0.54
    новниш
    0.53
    xen
    0.52
    ZEN
    0.51
    iren
    0.51
    vieren
    0.50
    igen
    0.49
    DebuggerNonUser
    0.48
    enable
    0.48
     glean
    0.47
    Activations Density 0.197%

    No Known Activations